CN115758476B - Electronic name seal manufacturing method, device and medium based on handwritten signature - Google Patents

Abstract

The application provides a method for manufacturing an electronic seal based on a handwritten signature, which is characterized in that a data terminal collects an electronic signature characteristic data sequence written by a user for many times, a multi-dimensional characteristic information signature point position sequence data packet is formed according to the electronic signature characteristic data sequence, the handwritten signature sequence data packet is constructed, signature patterns corresponding to different writing times are restored and displayed according to stroke characteristics in the handwritten signature data packet, one signature pattern is selected, a personal seal stamp is called, the selected restored signature pattern is matched with the position of the seal stamp, and the restored signature pattern is overlapped with a seal pattern layer to generate the personal electronic seal. The seal has individuation, solves the problem that the signer with the same name is difficult to distinguish, and prevents the forging of the seal to sign the document.

Description

Electronic name seal manufacturing method, device and medium based on handwritten signature

Technical Field

The invention relates to the technical field of computer information processing, in particular to a method for manufacturing a personal electronic name seal by using a handwriting signature.

Background

In the name part of the daily personal name seal, standard system microcomputer fonts such as Song Ti, bold and the like are usually used for generating seal stamps, and then the entity seals are carved through the stamps. When society enters an information age, when paper files become electronic documents, physical seals evolve into electronic seals, which naturally occur. The existing electronic seal is mostly manufactured by printing a seal shape by using an entity seal, then uploading seal information to a computer through scanning or photographing, and operating pictures by using professional software to form the electronic seal. The physical seal is simulated in an electronic mode, so that a user has application experience conforming to the traditional seal using habit in e-government affairs, e-commerce and other activities. However, this method has many drawbacks, including firstly a high requirement for the picture to be processed in the incoming computer software, and secondly, whether the picture is an entity seal or an electronic seal in the actual use process and the condition of having the same name, it is difficult to determine whether the picture is a seal of a designated party. Due to the specificity of the electronic document, the electronic seal is easier to forge by technical means. And the problem that the signers with the same name are difficult to distinguish is encountered, and the authenticity verification of the personal electronic name seal is problematic, so that difficulties are brought to dispute confirmation of electronic transactions, electronic contracts and the like after signing.

Publication number CN102542521a, entitled "an electronic stamp and electronic device", discloses an electronic stamp and electronic device having the same, comprising: selecting a seal character format, generating a seal layout and a seal pattern, combining the seal characters selected by the character selecting module with the seal layout and the seal pattern generated by the pattern generating module, and displaying the seal layout and the seal pattern. The electronic document is beautified, and the user experience is improved. However, since the template fonts are used and the standard templates are used for the seal fonts, the generated electronic seal cannot reflect the writing characteristics of a user, the specificity of an electronic document cannot be distinguished from signers with the same name, and the possibility that the electronic name seal is forged and used exists.

The Chinese patent with the publication number CN104537318A, named as an electronic seal dynamic generation system, takes a seal stamp template as a basis to obtain CN information of a signer or a unit from the seal certificate, draws a complete stamp picture on the seal stamp template according to display parameters, verifies a signature on the electronic seal, and displays the complete stamp picture after the verification is passed. The verification of the seal signature needs to use a complex algorithm and is difficult to realize.

CN113934993a is an electronic seal based on electronic handwriting signature technology, and the initiative biological feature of electronic handwriting signature data is used as a verification basis of use permission of the electronic seal. After the electronic seal generates a number for the signature object, identification data is added to the signed signature object. The signature is used for verifying the use permission of the seal, and the style and the characteristics of the personal handwriting signature cannot be reflected on the seal.

Other seals based on organization have high recognition degree and are easy to distinguish and recognize because special organization guarantees that the names of the seals are not repeated. However, the same situation of the personal name chapter may occur due to the possible existence of the duplicate name problem. This makes it difficult to distinguish and identify whether the current stamp is that of the intended signer, but each person's handwritten signature is different, with its own unique features, so that the handwritten signature is a packet containing the biometric information of the complete signer, and this packet is the first one. The average person can also determine whether the signer is a seal by signing the picture.

Because of the specificity of the electronic document, the electronic seal is more easily separated from the original signature object, and then the information such as abstract is forged by means such as database collision, etc., and the signature object is forged. Resulting in the case where the electronic seal is authentic, but the document of the signature object is counterfeit. The electronic seal can be manufactured by using the personal hand-written signature based on the unique characteristic of the hand-written signature, so that the occurrence of counterfeiting can be effectively prevented.

Disclosure of Invention

In view of the above, the present invention provides a method for making a personal name seal based on an original handwriting electronic signature. The method solves the problems that personal electronic name seal can not adopt personal pen signature and favorite style word, identification degree in actual use scene is not high, whether the personal electronic name seal is a signature of a signer can not be effectively identified, and the like.

According to one aspect of the application, the application provides a handwritten signature-based electronic seal manufacturing method, a data terminal collects an electronic signature characteristic data sequence written by a user for many times, a multidimensional characteristic information signature point position sequence data packet is formed according to the electronic signature characteristic data sequence, a handwritten signature sequence data packet is constructed, signature patterns corresponding to different writing times are restored and displayed according to stroke characteristics in the handwritten signature data packet, a signature pattern is selected, a personal seal stamp is called, the selected restored signature pattern is adapted to a seal pattern position, and the seal pattern layer is overlapped to generate a personal electronic seal.

Further preferably, the stacking of the selected signature pattern and the name seal stamp pattern layer includes adapting a suitable seal pattern template according to the position, character height and width of the restored back-displayed signature picture, or cutting the signature in the restored back-displayed signature picture into characters, and adapting and stacking each character and the seal pattern template to a suitable position.

Further preferably, the adapting to the position of the name seal die includes scaling the graph in which each character of the back-displayed electronic signature image is mapped to the two-dimensional plane, calculating the ratio of the character width to the height, converting the longest side to a fixed required length value, multiplying the short side by a corresponding scaling multiple under the condition that the aspect ratio is kept unchanged, obtaining normalized stroke track point coordinates, and mapping the stroke track point coordinates to the seal template.

Further preferably, the electronic signature characteristic data sequence includes a stroke sequence, a stroke pressure, a relative speed and an angular speed of an electronic signature, and generates the electronic signature characteristic data sequence based on a signature track point coordinate (x, y), time t, pressure p, angular speed v, relative angle a, pen down, pen up and pen up states s, and a handwriting signature sequence data packet [ [ x, y, t, p, v, a, s ] ] is constructed, wherein the states s are set to be (0, 1, 2) representing (pen down, pen up and pen up) states; and calculating writing speed by setting the time between the points through the strokes, and obtaining the light and heavy urgent information of the handwriting by combining the pressure information of the points, and controlling the thickness of the handwriting when the electronic signature is restored and redisplayed, wherein the point redisplayed with high pressure is a thick track, and the point redisplayed with low pressure is a thin track.

Further preferably, handwriting comparison and recognition are carried out on a plurality of handwriting signatures of the same content and a reserved signature of the signer in a database by using a character recognition network model crnn+ctc, signature sequence data packages of the same signer are confirmed, the signature sequence data packages are associated with signer information and signature identification codes are generated, track data in the plurality of signature sequence data packages are compared with standard track data, a data package closest to the standard track data is selected as an optimal signature data package, and signature angle speed characteristic information, namely stroke sequence, stroke pressure, stroke speed, relative speed and signature angle speed characteristic information, related to strokes in the optimal signature data package is obtained, and track restoration and back display are carried out, and signature tracks and signature patterns are displayed.

Further preferably, the signature track restoring and displaying adopts a Bezier curve Bezier interpolation algorithm to merge and supplement handwriting key points so as to smooth handwriting, and the thickness change of the strokes is determined according to the pressure value of the stroke track points to restore writing strokes; the method for restoring the back-display signature track by using the path arrangement and path conversion comprises the following steps: if the handwriting points acquired by acquiring the stroke track are dense and the path is continuous, replacing the part of the stroke track by a simplified path, if the acquired handwriting points are sparse, supplementing filling points on the stroke track, converting the path of the stroke track points into a renderable path, and generating a rendering path according to the pressure value of the writing stroke track points and the smoothness of the connection of all the stroke nodes.

Further preferably, a rendering path is generated by adopting a filling mode, for the filling points supplemented on the stroke track, the pressure value of each filling point is approximately calculated through the accumulated length of the stroke path, after the stroke path is straightened, the original track points A, B of the electronic signature strokes adjacent to the two sides of each filling point P are searched, and a formula is called according to the pressure values P (A) and P (B) of A, B points and the path positions l (A) and l (B):

ρ(P)＝ρ(A)+(ρ(B)-ρ(A))*(l(P)-l(A))/(l(B)-l(A))

linearly fitting the pressure value P (P) of the filling point P; and connecting each filling point with the previous node or the original handwriting point of the node by taking the filling point P as a node, forming a closed connecting line with the end point of the stroke, obtaining two path sequences which respectively represent the path profile from the starting point to the end point and from the end point to the starting point, and rendering the paths in different modes according to the shape of the filling point.

Further preferably, when the filling point is a rectangular point, the point is a point a when the directions of two sides passing through the end points of the stroke are consistent with the connecting line direction of the point, and when the two sides are inconsistent with the connecting line direction of the point, the point is a point C, two vertexes B and D respectively corresponding to the other rectangle are respectively added with an AB sequence, a DC connecting line is added with a DC sequence, a connecting line from the point C to the point a along the direction of the side of the rectangle is also added with the AB sequence for the starting point, and a connecting line from the point B to the point D is also added with the AB sequence for the ending point; when the filling point is an elliptic point, two connecting common tangents are designated as AB and DC connecting lines according to a direction consistency principle, AB and DC sequences are respectively added, an elliptic arc connecting line is used at the start point and the end point of the stroke, the intersection point of the front connecting line and the rear connecting line is calculated at the inner side of the middle point, the two connecting lines are connected at the intersection point, an elliptic arc is added between the two tangent points on the same ellipse at the outer side so as to close the path, and the smoothness of the stroke track is maintained.

Further preferably, stroke segmentation is performed through corner detection, a stroke starting point of each section is determined according to states of pen falling, pen running and pen lifting in an electronic signature sequence data packet, local curvature of the point is calculated according to front and rear coordinates of a stroke track point, a point with the maximum local curvature is used as a corner, and a track between the stroke starting point and the corner is segmented into a series of stroke sections; sequentially obtaining the maximum value and the minimum value of the abscissa in a series of stroke segments from the optimal data packet, and carrying out weighted average on the maximum value and the minimum value of the abscissa of all the stroke segments to be used as the width of signature characters; and sequentially acquiring the maximum value and the minimum value of the ordinate in a series of stroke segments, and carrying out weighted average on the maximum value and the minimum value of the ordinate of all the stroke segments to be used as the height of the signature character.

Further preferably, the fitting and superimposing each character and the stamp pattern template in the proper position includes rotating, stretching and tilting the entire character track according to the rotation factorDetermining the rotation angle of the character, and determining the coordinate point (x _i ,y _i ) The new coordinate points after rotation are: />Performing linear transformation on the abscissa or the ordinate of the coordinate point of the signature track, and according to the formula: (x) _i ×(1+α),y _i X (1+β)) calculate coordinates (x) _i ,y _i ) Stretching transformed coordinates, wherein the stretching coefficients are set to alpha and beta, respectively, ((alpha, beta) epsilon [ -1, 1)]) The method comprises the steps of carrying out a first treatment on the surface of the Coordinates (x) _i ,y _i ) The coordinates after the inclination change in the horizontal direction are: (x) _i ×(1+αx),y _i ) Coordinates (x) _i ,y _i ) The coordinates after the inclination change in the vertical direction are: (x) _i ,y _i ×(1+αy))。

According to another aspect of the present application, the present application proposes an electronic device comprising: a processor; and a memory storing a program, wherein the program comprises instructions that when executed by the processor cause the processor to perform the electronic signature making method based on handwritten signatures as described above.

According to another aspect of the present application, the present application proposes a non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform the electronic signature making method based on handwritten signatures according to the above.

By utilizing the special method that the identity of a signer can be identified by the handwriting signature, the handwriting signature is combined with the electronic seal to generate the electronic seal based on the handwriting signature, and the identity of the electronic seal can be identified. The personal name seal manufactured by using the impression generated by handwriting signature can greatly improve the recognition degree of the personal name seal, and can be clearly recognized after tracing the signature. The generated personal electronic name seal not only can ensure beautiful appearance and beautify the electronic document, but also has individuation, can easily distinguish the belonged condition of the electronic name seal, avoids the condition that the electronic name seal of the same-name user is similar, and solves the problem that the signer with the same name is difficult to distinguish. The electronic seal is manufactured by using the personal hand-written signature based on the unique characteristic of the hand-written signature, so that the occurrence of signing a document by using the forged seal can be effectively prevented.

Drawings

Further details, features and advantages of the present application are disclosed in the following description of exemplary embodiments, with reference to the following drawings, wherein:

FIG. 1 is a schematic flow chart of a method for creating a personal name seal according to an exemplary embodiment of the present application;

fig. 2 shows an electronic device according to an exemplary embodiment of the present application.

Detailed Description

Embodiments of the present application will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present application are shown in the drawings, it is to be understood that the present application may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but rather are provided to provide a more thorough and complete understanding of the present application. It should be understood that the drawings and examples of the present application are for illustrative purposes only and are not intended to limit the scope of the present application.

It should be understood that the various steps recited in the embodiments of the present application may be performed in a different order and/or performed in parallel. Furthermore, method embodiments may include additional steps and/or omit performing the illustrated steps. The scope of the present application is not limited in this respect.

The term "including" and variations thereof as used herein are intended to be open-ended, i.e., including, but not limited to. The term "based on" is based at least in part on. The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments. Related definitions of other terms will be given in the description below. It should be noted that the terms "first," "second," and the like herein are merely used for distinguishing between different devices, modules, or units and not for limiting the order or interdependence of the functions performed by such devices, modules, or units.

It should be noted that references to "one" or "a plurality" in this application are intended to be illustrative rather than limiting, and those of ordinary skill in the art will appreciate that "one or more" is intended to be interpreted as "one or more" unless the context clearly indicates otherwise.

The names of messages or information interacted between the various devices in the embodiments of the present application are for illustrative purposes only and are not intended to limit the scope of such messages or information.

Fig. 1 is a schematic flow chart of a method for manufacturing a personal name seal according to an exemplary embodiment of the present application, where the exemplary method mainly includes collection of a handwritten signature, display of a signature pattern, and manufacturing of a stamp.

The method comprises the steps of collecting handwriting signature characteristic data sequences of different writing modes and different styles of a user through a data collection terminal, then carrying out biological characteristic modeling, identifying and comparing on signatures, determining that handwriting signature data belong to the same person for signing, constructing a handwriting signature data packet according to the collected signature data sequences, restoring and displaying signature tracks and signature patterns corresponding to the different writing modes according to information such as stroke point position coordinates, pressure and speed in the handwriting signature data packet, selecting a signature pattern, calling a personal name seal stamp, and superposing the signature pattern and a name seal layer to generate a personal name seal.

And the signer carries out handwriting signature on the touch screen of the data acquisition terminal to obtain a handwriting electronic signature. The signature habits of each person are essentially different, such as the sequence of signature strokes, the writing strength, writing speed and writing angle of each stroke are different, the overall architecture of fonts and fonts is different, the thickness, trend and the like of the handwriting are also different, thus forming individual signatures with various characteristics, and the identity of each person can be accurately identified through the signatures. The electronic seal manufactured according to the signature also has respective styles and characteristics and can represent the identity of a person.

The signature acquisition module acquires biological characteristic information such as pen sequence, pen pressure, relative speed, angular speed and the like of an electronic signature of a signer in a signing process to generate characteristic parameters, and generates a signature sequence [ [ x, y, t, p, v, a fault, s ] ] based on the characteristic parameters including signature track point coordinates (x, y), time t, pressure p, angular speed v, relative angle a, pen-down, pen-up lifting state s and the like, wherein the state s can be set to be (0, 1, 2) to represent (pen-down, pen-up) states. And forming a multi-dimensional characteristic information signature point position sequence data packet of the signer according to the characteristic parameters of the electronic signature stroke track, and storing the multi-dimensional characteristic information signature point position sequence data packet in a database.

The sequence data packet comprises coordinate points of metadata of the electronic signature, and the group of data corresponds to a unique signature picture and can be used as a unique identifier of the electronic signer. And restoring the electronic signature track through writing stroke point coordinates, writing time, pen-down, pen-up and pen-up states in the data packet signature sequence, and restoring the signature track of the signer.

In the process of collecting electronic signatures, the same signer can conduct multiple signatures, (for example, at least 3 signatures can be conducted on different signing devices), the same person can use multiple signatures of different signing modes, different signing styles and the like to form a plurality of signature sequence data packages, the crnn+ctc text recognition network model can be used for comparing and recognizing the signature sequence data packages with reserved signatures of the signer in a database, the data packages generated by the fact that the signature data packages are the same signer signature are confirmed, the signature sequence data packages are associated with signer information in the reserved database to generate signature identification codes, the Chinese character segmentation method based on the bert sequence labeling task is used for restoring a plurality of handwriting pictures, and the handwriting pictures are displayed to the signer through comparison with preset standard data in the signature data packages through writing tracks.

And calling fonts in a font library to set standard track data, comparing track data in a plurality of signature sequence data packets with the standard track data, selecting a data packet closest to the standard track data as an optimal data packet, calling the optimal signature data packet, and acquiring signature characteristic information such as stroke sequence, stroke pressure, stroke speed, relative speed, angular speed and the like in the signature sequence data to carry out back display, display the signature track and the formed signature pattern.

Handwriting recovery is the process of converting an ordered series of coordinate sampling points into a continuous line curve of strokes. The two most critical effects of handwriting restoration are smoothness and strokes, and the writing style can be well reflected by the two effects. To achieve smoothing, some tidying is needed to be carried out on the input handwriting, some points are combined or some points are supplemented, key points of the handwriting can be combined and supplemented through a Bezier interpolation algorithm, the strokes are restored, the pressure value is mainly processed in a fine mode, the thickness change of the strokes can be restored, and meanwhile the thickness change is smoothed as much as possible.

Therefore, when the signature track is restored and back displayed, the Bezier interpolation algorithm is adopted to merge and supplement the key points of the handwriting so as to smooth the handwriting, and the thickness change of the strokes is determined according to the writing pressure value to restore the writing strokes.

The handwriting reduction scheme of the embodiment of the application can output the signature graph by using a method comprising 'path sorting' and 'path conversion'.

For the original path, if the handwriting points of a certain path are input in a denser way and the path is continuous, the simplified path can be used for replacing the path, so that the calculation and rendering performance can be improved, and the influence caused by sampling noise (local slight convex points) and sampling precision is reduced. If the handwriting points of a certain path are sparse, some points need to be supplemented on the path so as to achieve the effects of reducing curvature and increasing smoothness.

In the "path conversion" phase, the path of the handwriting point is converted into a renderable path, and pressure values need to be processed and smoothness of connection of each node is considered. Generating a rendering path according to the pressure value of the writing points and the smoothness of the connection of all stroke nodes, and displaying by a rendering module after generating the rendering path, wherein the path rendering generally adopts two modes of profile and filling, and the filling mode is adopted because the profile rendering can involve various linear style configurations and the rendering realization is inconsistent; the filling mode is simple and clearly suitable for a rendering mode of the character font, and because the filled points are not stroke original points, no additional pressure information is needed, the pressure information of each point needs to be recovered, and the pressure value of each Bezier filling point is approximately calculated through the path accumulation length. The length of the path is unchanged after the path filling point is finished.

After the stroke path is straightened, each Bezier filling point P (position l (P)) must be between two adjacent writing original points A, B, and the pressure values P (a), P (B) and path positions l (a), l (B) of A, B points are passed according to the formula: ρ (P) =ρ (a) + (ρ (B) - ρ (a)) (l (P) -l (a))/(l (B) -l (a))

The pressure value P (P) at point P is linearly fitted.

The filling points on the Bezier path are used as nodes, each Bezier filling point is connected with the last node or the original handwriting point of the node (not necessarily the last point of the Bezier path), and a closed connecting line is formed with the end point of the stroke. Because a surrounding path is finally generated, two path sequences are needed to represent the path profile from the start point to the end point and from the end point to the start point, respectively. These two sequences are called AB sequence, DC sequence, respectively. When generating the enclosed path, the shape of the filling point (rectangle, ellipse) needs to be considered, and different processing methods are used for different point shapes.

For a rectangular point, when the directions of two sides passing through a certain vertex are consistent with the connecting line direction of the point, the point is a point A; when the points are inconsistent, the point is a point C, and the points correspond to a point B and a point D of the vertex of the other rectangle respectively; the AB link joins the AB sequence and the DC link (reverse) joins the DC sequence. For the starting point, adding an AB sequence into a connecting line from the point C to the point A along the direction of the rectangular edge; for the end point, the AB sequence was also added to the line from point B to point D.

For the elliptical dot, two connecting common tangents are arranged, and are designated as AB and DC lines according to the principle of direction consistency, and AB and DC sequences are respectively added. However, at the starting point and the end point, there is an elliptical arc connecting line, at the middle point, according to the change of the node direction, the processing needs to be performed on the inner side and the outer side, the intersection point of the front and the rear connecting lines (two DC lines) needs to be calculated on the inner side, and the two connecting lines are connected at the intersection point; the outside needs to add an elliptical arc between two tangent points (on the same ellipse) to close the path and maintain the smoothness of the path.

The design database is imported with a pre-designed personal name seal design template, the personal name seal design template is stored in an image format, the design template is called, an optimal signature data packet is matched and selected, and a signature image can be combined with different design templates. The signature image track can be rendered red and superimposed on the pattern templates to form the signature style of the signature image track and the name chapter styles of different pattern templates, and the signature image track and the name chapter styles are displayed on a terminal screen. When the image is restored, the signature is restored according to the same proportion as the size of the signature required by the template.

The signature trace is adaptively adjusted so that the signature is in the proper position in the chapter. When the personal signature image is overlapped with the personal name seal pattern template, the personal name seal pattern template is required to be matched with a proper seal pattern template according to various pattern templates, the processed signature position, character height, character width and the like, the signature can be segmented into characters, and the characters are matched with the proper positions of the seal pattern template.

One method for determining signature characters in the processing of the embodiment is to traverse the abscissa and the ordinate of each character in the signature optimal data packet to obtain the maximum value and the minimum value of the abscissa and the ordinate, and estimate the width and the height of the whole signature according to the maximum and the minimum values of the coordinates.

One method for processing signature characters in the embodiment is to split strokes through corner detection, cut the strokes from the corners to generate new relatively short stroke segments, determine the starting point of each stroke according to the states of pen down, pen up and pen up in a signature sequence data packet, calculate the local curvature of the point according to the front and back coordinates of the stroke track point, take the point with the maximum local curvature as the corner, and split the signature track between the starting point of the stroke and the corner into a series of stroke segments.

Sequentially obtaining the maximum value and the minimum value of the abscissa in a series of stroke segments from the optimal data packet, and carrying out weighted average on the maximum value and the minimum value of the abscissa of all the stroke segments to be used as the width of signature characters; and sequentially acquiring the maximum value and the minimum value of the ordinate in a series of stroke segments, and carrying out weighted average on the maximum value and the minimum value of the ordinate of all the stroke segments to be used as the height of the signature character.

Scaling the graph of mapping each character of the back-display electronic signature image to a two-dimensional plane, calculating the ratio of the character width to the height, converting the longest edge into a length value required by fixing, and multiplying the short edge by a corresponding scaling multiple under the condition of keeping the aspect ratio unchanged.

One method of signature processing in this embodiment is to traverse the coordinates (xi, yi) of the stroke trace points of each character to obtain the maximum and minimum abscissa xmax, xmin and ordinate ymax, ymin of the character, according to the formula: and calculating the character width w and the height h by w=xmax-xmin and h=ymax-ymin, and then stretching the long side max (w, h) of the character to a fixed value Q, and expanding the short side by corresponding times to obtain the normalized stroke track point coordinates.

Rotating, stretching and tilting the whole character track according to the rotation factorDetermining a character rotation angle, and for any point i coordinate point (xi, yi) of a signature track, determining that a new coordinate point after rotation is:

stretching is to perform linear transformation on the abscissa or the ordinate of the sign trace coordinate point, and the stretching coefficients are respectively set to be alpha and beta, wherein (([ alpha, beta ])epsilon < -1,1 ]). According to the formula: (xi× (1+α), yi× (1+β)) coordinates (xi, yi) after stretching transformation.

The coordinates (xi, yi) after the inclination change in the horizontal direction are: (xi× (1+αx), yi), coordinates after the inclination change in the vertical direction of the coordinates (xi, yi) are: (xi, yi× (1+αy)).

And filling up the edge blank pixels. In order to keep the edge path characteristics of the image not lost due to convolution operation when the bert sequence of the signature image is marked, blank pixel filling is carried out on the signature image.

The signer can independently select pattern templates in the pattern database according to the displayed seal name style, and can preview the electronic stamp samples formed by combining the signature with different pattern templates on line. And calling biological characteristic information such as the pen sequence, pen pressure, pen speed, relative speed, angular speed and the like of the signature of the signer obtained through signature acquisition to generate characteristic parameters, and restoring the electronic signature handwritten by the signer by using a Chinese character segmentation method based on a bert sequence labeling task.

The method comprises the steps of combining multidimensional characteristic information such as handwriting signature sequences, pen pressures, pen numbers and the like acquired from a touch screen, calculating writing speed through time among stroke set points, combining the point pressure information to obtain light and heavy urgent information of handwriting, further controlling handwriting thickness during signature back display, enabling points with high pressure to be displayed back to be a thick track, enabling points with low pressure to be displayed back to be a thin track, and carrying out handwriting drawing according to a coordinate point moving track formed by signature strokes on the touch screen to restore a signature track of a signer.

And fusing the restored handwriting picture with a pattern template selected by a signer in advance by using a picture synthesis technology of image fusion to synthesize a stamp of the name seal. Finally, the bt picture seed compression method is adopted to compress the picture and the information about signers in one picture, and the picture can be decompressed at necessary time to distinguish the genuine-fake of the seal, so as to achieve the purpose of distinguishing the genuine-fake of the seal and prevent counterfeiting.

The exemplary embodiment of the application also provides an electronic device, including: at least one processor; and a memory communicatively coupled to the at least one processor. The memory stores a computer program executable by the at least one processor for causing the electronic device to perform a method according to an embodiment of the present application when executed by the at least one processor.

The present exemplary embodiments also provide a non-transitory computer readable storage medium storing a computer program, wherein the computer program, when executed by a processor of a computer, is for causing the computer to perform a method according to an embodiment of the present application.

The present exemplary embodiments also provide a computer program product comprising a computer program, wherein the computer program, when being executed by a processor of a computer, is for causing the computer to perform a method according to embodiments of the present application.

Referring to fig. 2, a block diagram of an electronic device 300 that may be a server or client of the present application, which is an example of a hardware device that may be applied to aspects of the present application, will now be described. Electronic devices are intended to represent various forms of digital electronic computer devices, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the application described and/or claimed herein.

As shown in fig. 2, the electronic device 300 includes a computing unit 301 that can perform various suitable actions and processes according to a computer program stored in a Read Only Memory (ROM) 302 or a computer program loaded from a storage unit 308 into a Random Access Memory (RAM) 303. In the RAM303, various programs and data required for the operation of the device 300 may also be stored. The computing unit 301, the ROM302, and the RAM303 are connected to each other by a bus 304. An input/output (I/O) interface 305 is also connected to bus 304.

Various components in the electronic device 300 are connected to the I/O interface 305, including: an input unit 306, an output unit 307, a storage unit 308, and a communication unit 309. The input unit 306 may be any type of device capable of inputting information to the electronic device 300, and the input unit 306 may receive input numeric or character information and generate key signal inputs related to user settings and/or function controls of the electronic device. The output unit 307 may be any type of device capable of presenting information and may include, but is not limited to, a display, speakers, video/audio output terminals, vibrators, and/or printers. Storage unit 308 may include, but is not limited to, magnetic disks, optical disks. The communication unit 309 allows the electronic device 300 to exchange information/data with other devices through a computer network, such as the internet, and/or various telecommunications networks, and may include, but is not limited to, modems, network cards, infrared communication devices, wireless communication transceivers and/or chipsets, such as bluetooth devices, wiFi devices, wiMax devices, cellular communication devices, and/or the like.

The computing unit 301 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 301 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 301 performs the respective methods and processes described above. For example, in some embodiments, the secure electronic document forming method may be implemented as a computer software program tangibly embodied on a machine-readable medium. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 300 via the ROM302 and/or the communication unit 309. In some embodiments, the computing unit 301 may be configured to perform the computation of the file hash value by any other suitable means (e.g. by means of firmware).

Program code for carrying out methods of the present application may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus such that the program code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this application, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or device (e.g., magnetic discs, optical disks, memory, programmable Logic Devices (PLDs)) used to provide machine instructions and/or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the internet.

The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.

Claims (11)

1. The electronic signature making method based on the handwritten signature is characterized in that a data terminal collects an electronic signature characteristic data sequence written by a user for many times, forms a multi-dimensional characteristic information signature point position sequence data packet according to the electronic signature characteristic data sequence, constructs a handwritten signature sequence data packet, compares and identifies a plurality of electronic signatures of the same content with reserved signatures in a database by handwriting, associates the signature sequence data packet of the same signer with signer information to generate a signature identification code, restores and displays signature patterns corresponding to different writing times according to the stroke characteristics in the electronic signature data packet, selects a signature pattern, calls a personal signature stamp, adapts the selected signature pattern to a name stamp position, and overlaps the signature pattern with a stamp layer to generate a personal electronic signature; the selecting one signature pattern includes: setting standard track data by calling fonts in a font library, comparing track data in a plurality of signature sequence data packets with the standard track data, selecting a data packet closest to the standard track data to acquire signature sequence data characteristic information, and carrying out restoration display and signature track display to form a signature pattern; the step of restoring and displaying the signature patterns corresponding to different writing times comprises the steps of merging and supplementing key points of handwriting by adopting a Bezier curve interpolation algorithm to enable the track to be smooth, and determining the thickness change of the strokes according to the track point pressure value to restore the writing strokes; for the complementary key points, calculating the pressure value of each filling point through the accumulated length of the stroke track, straightening the stroke track, searching the original track points of the adjacent strokes on both sides of each filling point, and linearly fitting the pressure value of the filling point according to the pressure values and the positions of the adjacent original stroke track points; and taking the filling points as nodes, connecting each filling point with the previous node or the original track point of the node, forming a closed connecting line with the stroke end point, and rendering the stroke track according to the shape of the filling point, wherein the two path sequences respectively represent the stroke outline from the starting point to the end point and from the end point to the starting point.

2. The method of claim 1, wherein stacking the selected signature pattern with the name-stamp layer includes adapting an appropriate stamp pattern template based on the position of the reduced display signature pattern, the character height, the width, or segmenting the signature in the reduced display signature pattern into characters, and adapting each character with the stamp pattern template to be stacked in place.

3. The method of claim 1, wherein said adapting the position of the stamp name module includes scaling the graphic that the characters of the restored display electronic signature image are mapped to the two-dimensional plane, calculating the ratio of the character width to the height, converting the longest side to a fixed desired length value, multiplying the shorter side by a corresponding scaling factor while maintaining the aspect ratio, obtaining normalized stroke track point coordinates, and mapping the stroke track point coordinates to the stamp template.

4. A method according to any one of claims 1-3, wherein the electronic signature feature data sequence comprises a sequence of electronic signatures, a stroke, a relative velocity, an angular velocity, generating an electronic signature feature data sequence, constructing a handwritten signature sequence data packet based on signature trace point coordinates (x, y), time t, pressure p, angular velocity v, relative angle, stroke up state s; and calculating writing speed by setting the time between the points through the strokes, and obtaining the light and heavy urgent information of the handwriting by combining the pressure information of the points, and controlling the thickness of the handwriting when the electronic signature is restored and redisplayed, wherein the point redisplayed with high pressure is a thick track, and the point redisplayed with low pressure is a thin track.

5. A method according to any one of claims 1-3, characterized in that the reproduction of the stroke track is performed using a method comprising path sorting and path conversion, in particular comprising: if the stroke track points acquired by acquiring the stroke track are dense and the path is continuous, replacing the part of the stroke track by a simplified path, if the acquired stroke track points are sparse, supplementing filling points on the stroke track, converting the path of the stroke track points into a renderable path, and generating a rendering path according to the pressure value of the writing stroke track points and the smoothness of the connection of all the stroke nodes.

6. The method of claim 5, wherein a rendering path is generated using a fill pattern, and wherein formulas are called according to pressure values p (a), p (B) and path positions l (a), l (B) of an original stroke track point A, B points:

fitting the pressure value of the filling point P linearlyp(P), wherein l (P) is the filling point P position.

7. The method of claim 6, wherein when the filling point is a rectangular point, the point is a point when the directions of two sides passing through the end points of the stroke are consistent with the connecting line direction of the point, the point is a point, and when the directions of the two sides passing through the end points of the stroke are inconsistent with the connecting line direction of the point, the point is a point C, two vertexes B and D respectively corresponding to another rectangle are respectively added with an AB sequence, a DC connecting line is added with a DC sequence, for the starting point, a connecting line from the point C to the point A along the direction of the side of the rectangle is also added with the AB sequence, and for the ending point, a connecting line from the point B to the point D is also added with the AB sequence; when the filling point is an elliptic point, two connecting common tangents are designated as AB and DC connecting lines according to a direction consistency principle, AB and DC sequences are respectively added, an elliptic arc connecting line is used at the start point and the end point of the stroke, the intersection point of the front connecting line and the rear connecting line is calculated at the inner side of the middle point, the two connecting lines are connected at the intersection point, an elliptic arc is added between the two tangent points on the same ellipse at the outer side so as to close the path, and the smoothness of the stroke track is maintained.

8. The method according to one of claims 1-3,6, wherein the stroke segmentation is performed by corner detection, the starting point of each stroke is determined according to the states of pen down, pen up and pen up in the electronic signature sequence data packet, the local curvature of the point is calculated by the front and back coordinates of the stroke track point, the point with the largest local curvature is taken as the corner, and the track from the starting point of the stroke to the corner is segmented into a series of stroke segments; sequentially obtaining the maximum value and the minimum value of the abscissa in a series of stroke segments from the optimal data packet, and carrying out weighted average on the maximum value and the minimum value of the abscissa of all the stroke segments to be used as the width of signature characters; and sequentially acquiring the maximum value and the minimum value of the ordinate in a series of stroke segments, and carrying out weighted average on the maximum value and the minimum value of the ordinate of all the stroke segments to be used as the height of the signature character.

9. The method of claim 2, wherein the adaptively superimposing each character and the stamp pattern template in place includes rotating, stretching, tilting the entire character track, determining a character rotation angle according to a rotation factor ʊ, and for any point i coordinate point (xi, yi) of the signature track, the new coordinate point after rotation is: (xi×cos (ʊ) +yi×sin (ʊ), -xi×sin (ʊ) +yi×cos (ʊ)), linearly transforming the abscissa or ordinate of the sign-locus coordinate point according to the formula: (xi x (1+α), yi x (1+β)) calculate coordinates (xi, yi) the stretch-transformed coordinates, wherein the stretch coefficients are set to α and β, ((α, β) ∈ [ -1,1 ]); the coordinates (xi, yi) after the inclination change in the horizontal direction are: (xi× (1+αx), yi), coordinates after the inclination change in the vertical direction of the coordinates (xi, yi) are: (xi, yi× (1+αy)).

10. An electronic device, comprising: a processor; and a memory storing a program, wherein the program comprises instructions that when executed by the processor cause the processor to perform the handwritten signature-based electronic signature production method according to any one of claims 1-9.

11. A non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform the handwritten signature-based electronic signature generation method according to any one of claims 1-9.